Unable to run pmlc-opt output MLIR example via pmlc-jit about plaidml HOT 2 OPEN

within split at pmlc/target/x86/tests/reorder_layouts.mlir:1 offset :27:8: error: 'linalg.generic' op expects regions to end with 'linalg.yield', found 'llvm.return'
  %2 = linalg.generic {
       ^
within split at pmlc/target/x86/tests/reorder_layouts.mlir:1 offset :27:8: note: see current operation: %8 = "linalg.generic"(%4, %6, %7) ( {
^bb0(%arg3: f32, %arg4: f32, %arg5: f32):  // no predecessors
  %12 = "std.mulf"(%arg3, %arg4) : (f32, f32) -> f32
  %13 = "std.addf"(%arg5, %12) : (f32, f32) -> f32
  "llvm.return"(%13) : (f32) -> ()
}) {indexing_maps = [affine_map<(d0, d1, d2, d3, d4, d5, d6, d7, d8) -> (d0, d8, d1 + d4, d2 + d5, d6)>, affine_map<(d0, d1, d2, d3, d4, d5, d6, d7, d8) -> (d8, d7, d4, d5, d6, d3)>, affine_map<(d0, d1, d2, d3, d4, d5, d6, d7, d8) -> (d0, d7, d1, d2, d3)>], iterator_types = ["parallel", "parallel", "parallel", "parallel", "reduction", "reduction", "reduction", "parallel", "reduction"], operand_segment_sizes = dense<[2, 1]> : vector<2xi32>} : (tensor<1x4x56x56x16xf32>, tensor<4x4x1x1x16x16xf32>, tensor<1x4x56x56x16xf32>) -> tensor<1x4x56x56x16xf32>
within split at pmlc/target/x86/tests/reorder_layouts.mlir:1 offset :27:8: note: in custom textual format, the absence of terminator implies 'linalg.yield'

%2 = linalg.generic {
    indexing_maps = [#input, #filter, #output],
    iterator_types = ["parallel", "parallel", "parallel", "parallel", "reduction", "reduction", "reduction"]
  } ins(%arg0, %arg1 : tensor<1x56x56x64xf32>, tensor<1x1x64x64xf32>) outs(%1 : tensor<1x56x56x64xf32>) {
  ^bb0(%arg3: f32, %arg4: f32, %arg5: f32):  // no predecessors
    %5 = mulf %arg3, %arg4 : f32
    %6 = addf %arg5, %5 : f32
    linalg.yield %6 : f32
  } -> tensor<1x56x56x64xf32>